ClawHub
Back to skill

Security audit

胡田 OPC导师 SPV治理

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple text-only SPV document helper, but it may produce high-stakes legal and financial templates without clear legal-review or jurisdiction safeguards.

Review this skill carefully before installing. It does not appear to contain code-level security threats, but its outputs could affect legal rights, ownership, revenue sharing, exits, and disputes. Treat any generated documents as draft templates only, specify jurisdiction and facts clearly, and have qualified counsel review before signing or relying on them.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly promotes using AI to generate a complete set of SPV governance documents in one hour, but provides no warning about legal accuracy, jurisdictional variation, enforceability, or the need for professional review. In context, this is especially risky because the generated output includes contracts, IP ownership, confidentiality, non-compete, exit, and dispute-resolution terms that can create serious legal and financial harm if wrong or inapplicable.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad, generic business/legal prompts such as forming a project entity, drafting cooperation agreements, or designing profit-sharing. This makes unintended invocation likely, which is dangerous here because the skill can generate quasi-legal governance artifacts for users who may not realize they are receiving specialized legal/structuring guidance.

Content

No source excerpt is available for this finding.